© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21151
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or organizations, particularly with the name "Crist"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Crist" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fertility
    -0.77
    é¾įå¥ij士
    -0.74
     foreskin
    -0.72
     UCHIJ
    -0.69
    ãĥł
    -0.67
    UGH
    -0.67
     shred
    -0.66
    «ĺ
    -0.65
     subscribe
    -0.65
     gearing
    -0.64
    POSITIVE LOGITS
    obal
    1.36
    anos
    0.92
    ea
    0.90
    ez
    0.90
    iano
    0.89
    lia
    0.86
    stal
    0.85
    ept
    0.84
    ÃŃa
    0.83
    ophon
    0.82
    Activations Density 0.037%

    No Known Activations